INDEX

Explanations

references or descriptions related to arrows

oai_token-act-pair · gpt-3.5-turbo

references to arrows indicating direction or movement

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.1.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

inen

-0.79

nesota

-0.73

ĨĴ

-0.69

idential

-0.68

issue

-0.66

idency

-0.65

ĸļ

-0.64

zzo

-0.64

umbled

-0.63

issued

-0.62

POSITIVE LOGITS

 arrow

1.47

 arrows

1.30

 Arrows

0.96

 Arrow

0.93

smith

0.89

 shaft

0.89

heads

0.85

wright

0.84

bolt

0.83

arrow

0.82

Activations Density 0.006%

references or descriptions related to arrows

references to arrows indicating direction or movement

No Comments

No Known Activations